Adversarial Attack against Cross-lingual Knowledge Graph Alignment
Recent literatures have shown that knowledge graph (KG) learning models are highly vulnerable to adversarial attacks. However, there is still a paucity of vulnerability analyses of cross-lingual entity alignment under adversarial attacks. This paper proposes an adversarial attack model with two novel attack techniques to perturb the KG structure and degrade the quality of deep cross-lingual entity alignment. First, an entity density maximization method is employed to hide the attacked entities in dense regions in two KGs, such that the derived perturbations are unnoticeable. Second, an attack signal amplification method is developed to reduce the gradient vanishing issues in the process of adversarial attacks for further improving the attack effectiveness.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackEntity AlignmentSimilar Papers 제목 키워드 기반
A Generative Adversarial Attack for Multilingual Text Classifiers
Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks, however, generally assume that the vict…
Adversarial AttackLost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation
Language Models today provide a high accuracy across a large number of downstream tasks. However, they remain susceptible to adversarial attacks, particularly against those where the adversarial examples maintain conside…
Machine TranslationTranslationTowards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversariall…
Instruction FollowingSafety AlignmentCode-Mixing on Sesame Street: Dawn of the Adversarial Polyglots
Multilingual models have demonstrated impressive cross-lingual transfer performance. However, test sets like XNLI are monolingual at the example level. In multilingual communities, it is common for polyglots to code-mix …
Cross-Lingual TransferXLM-RBadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
In this paper, we present a new form of backdoor attack against Large Language Models (LLMs): lingual-backdoor attacks. The key novelty of lingual-backdoor attacks is that the language itself serves as the trigger to hij…
Backdoor Attack